{"id":"W4234274521","doi":"10.5194/isprsannals-iii-3-123-2016","title":"REVISITING INTRINSIC CURVES FOR EFFICIENT DENSE STEREO MATCHING","year":2016,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre de Géomatique du Québec; York University; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Pixel; Computer vision; Matching (statistics); Computer science; Regularization (linguistics); Ambiguity; Photogrammetry; Mathematics; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00133625,0.0008757351,0.0009211264,0.001815668,0.0005735603,0.001428476,0.001887501,0.001354704,0.002435925],"category_scores_gemma":[0.005210087,0.0006369899,0.0008832761,0.001433778,0.0008650474,0.002749854,0.002651492,0.001562994,0.0009712791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008541035,"about_ca_system_score_gemma":0.001591536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003223401,"about_ca_topic_score_gemma":0.003431968,"domain_scores_codex":[0.9988756,0.0001610011,0.00005101075,0.0002030871,0.0006013818,0.0001080067],"domain_scores_gemma":[0.9982222,0.000562051,0.0001813443,0.0004536845,0.0005035597,0.0000770991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008635595,0.0000967998,0.001274935,0.000135477,0.00003551837,0.0000842813,0.0002611721,0.4204845,0.04025453,0.04687653,0.001642612,0.4887672],"study_design_scores_gemma":[0.000006186185,0.00003100455,0.0001621755,0.000008672638,0.000004111941,0.00004744472,0.00002053929,0.9810557,0.005320438,0.01169525,0.001639204,0.000009280012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005985434,0.00004145693,0.9931552,0.00003935344,0.000006531716,0.0000200573,0.00001978332,0.00021369,0.0005184575],"genre_scores_gemma":[0.1563581,0.0001468264,0.8419342,0.00005489369,0.0000291643,0.0000676997,0.0001767371,0.0001966361,0.001035733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003223401,"threshold_uncertainty_score":0.008148968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04343993242007997,"score_gpt":0.3239632465355918,"score_spread":0.2805233141155118,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}